generate-project-dashboard
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from the user's Obsidian vault to drive its workflow.
- Ingestion points: Reads project notes, meeting notes, and daily notes from the vault as described in
SKILL.md. - Boundary markers: There are no defined delimiters or instructions to the agent to disregard instructions found within the ingested note content.
- Capability inventory: The skill can perform file system writes (updating Markdown and HTML files) and execute Chromium for screenshot generation (referenced in
SKILL.md). - Sanitization: There is no mention of sanitizing or validating the content extracted from notes before it is used to generate the dashboard or update the project note.
Audit Metadata